feat(cli): hand off onboarding to your coding agent#60
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
Reworks the
dlthub-startonboarding so the CLI sets the workspace up and then hands off to your coding agent, instead of running the sample pipeline and opening the dashboard itself. Also tightens the setup output and copy so the run reads cleanly.Changes
Flow (
cli.py)playgroundworkspace, the CLI hands off to the chosen agent rather than runningload_sample_shop/ opening the dashboard.deploy-run-sample-pipelineskill) or skip and get the prompt printed + copied to paste into an agent yourself.dlthubCLI works).uv syncfailure still exits with the error (no CLI = no hand-off).uv syncinto one step and login + playground connection into another; login runs quietly (output surfaces only on error).Copy (
strings.py)Other modules
display.py:print_next_stepstakesagent_prompt+panel_title.prompts.py:confirm()supports custom yes/no labels.config.py: addedAGENT_SKILLS_DIR(drift-checked against the scaffold); bumpedWORKBENCH_REF.Docs
workspace-hereMakefile help, thepyprojectdescription, and the CHANGELOG to match the new flow; fixed stale--yes/--skip-uv-syncreferences (now--setup-only/--scaffold-only) and the codex.agents/directory.Bundled workbench
_agents/**from the bumpedWORKBENCH_REF: thetoolkit-dispatchskill is nowdlthub-router, which routes to and installs the right workflow toolkit on demand. Refreshed the scaffolduv.lock(dlt1.28.1).Tests
test_cli.py,test_display.py,test_config.py,test_prompts.pycovering the hand-off paths (launch / decline / unlaunchable agent / non-TTY / login-failure resolve), the outcome panel titles, the quiet login, and theAGENT_SKILLS_DIRmapping.133 passed;ruffandmypyclean.make workspace-localend-to-end (scaffold → quiet login/connect → hand-off).